Claude Sonnet 4 (20250514): benchmark results
May 14, 2025 Claude Sonnet 4 snapshot, tracked when sources report the dated API model. Provider: Anthropic. Released 2025-05-14. Access: API.
Unified ELO 1619 ± 1, rank #210 of 1392 rated models, from 113 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Galileo Agent - Healthcare TSQ | 95 | Task Success Quality (%) | 100 |
| Galileo Agent - Healthcare Accuracy | 62 | Accuracy (%) | 97.6 |
| Enkrypt AI - Safety Risk | 14.32 | Risk Score | 96.9 |
| HELM AIR-Bench | 88.3 | Refusal Rate (%) | 96.5 |
| HELM Safety BBQ | 97.9 | BBQ accuracy (%) | 94.8 |
| Enkrypt AI - Toxicity Risk | 0.23 | Risk Score | 92.9 |
| Galileo Agent - Banking Accuracy | 58 | Accuracy (%) | 92.9 |
| Web-Bench | 25.1 | Pass@1 (%) | 92.6 |
| HAL Online Mind2Web | 40 | Accuracy (%) | 90.9 |
| RewardBench Factuality | 76.12 | Accuracy (%) | 90.8 |
| RewardBench Math | 70.49 | Score (%) | 90.6 |
| Galileo Agent - Insurance TSQ | 93 | Task Success Quality (%) | 90.5 |
Interactive version: theaggregate.ai/model?slug=claude-sonnet-4-20250514 · How It Works · Data refreshed daily, snapshot 2026-09-05.